Results for “intent-recognition”

Turn accepted search evidence into an intent, competitor, and information-gain brief.

NIH grant research skill for clinical researchers. Grill-me intake (research idea + career stage + preliminary data + environment + submission posture + known institute targets) locks down the funding strategy before any search runs. Runs a 5-facet Consensus positioning analysis (with draft Significance/Innovation language), maps the research to the right NIH institutes and study sections via RePORTER, finds NOSIs and funded overlap, and produces an editable Word document (.docx) with budget/scope-aware mechanism recommendations, submission timelines, and a mandatory program officer recommendation. Use when the user asks about research funding or makes any grant-related request (e.g., 'grants for [topic]', 'find grants for my research idea', 'what grants match my research', 'help me find NIH funding', 'grant opportunities for my research'). NIH-only scope — non-NIH funders (PCORI, DOD CDMRP, VA, foundations) are out of scope and flagged at intake.

Locates files by intent using semantic search, ideal for finding implementations, definitions, or documentation in medium to large repositories.

Finds gaps between documented intent and actual implementation in codebases, catching bugs that generic scanners miss because they lack a model of intent.

Use `analysis-agent` when engineering intent lacks desired behavior, boundaries, constraints, or completion signals. Skip requests with an accepted Engineering Brief and no-repo direct-answer work.

Detect and resolve naming collisions, overlapping intent triggers, and insufficient intent diversity across the skill library. Load when a new skill is created (called by universal-skill-creator), during improvement passes (called by improve-skills), or when the user asks to deconflict skills, check for naming collisions, audit trigger overlap, review intent coverage, find duplicate triggers, check skill names, or says "are any skills too similar", "which skills overlap", "deconflict the library", "check for confusing skill names", "intent audit".

Hunt for Mimikatz execution using command-line patterns, LSASS access signatures, binary indicators, and in-memory detection of known modules.

Classify, prioritize, and route incoming support tickets by extracting intent and entities, assigning severity, and generating initial responses. Use when the user requests ticket triage or provides relevant inputs for this workflow.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

Shape or refine the existing bead or caller intent without creating a second planning artifact. Triggers: "plan", "discover and plan", "shape this goal".

Collects publicly available information about a target organization to identify attack surfaces, social engineering targets, technology stacks, and credential exposures for authorized security testing.

Research companies, industries, or competitor sets using web search and seven analytical lenses to produce structured intelligence for downstream product management tasks.

当需要主动从海量信息中寻找能带来深刻启发、挑战现有认知或激发好奇心的新想法时

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

Hunt for spearphishing campaign indicators across email logs, endpoint telemetry, and network data to detect targeted email attacks.

Recommends the best skill, agent, or command for a given task by classifying intent and scanning available tools.

Interviews users to capture creative intent for video projects, producing a structured creative brief and unresolved blockers list before editing begins.

Translates user intent into a precise, unambiguous specification and requirements.

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. Use when developing students' thinking-about-thinking during independent work.

Extracts the user's true intent through one-question-at-a-time interviews, surfacing hidden assumptions before any plan or code is written.

Harness Router

当面临信息过载或想法过多，需要筛选出值得投入资源（时间、精力）去执行的高价值想法时

Execution discipline with agency, instinct detection, critical safety rules, trust layer, and error resilience. v2.7 adds timeout handling, checkpointing, and decision logging.

NIH grant research skill for clinical researchers. Grill-me intake (research idea + career stage + preliminary data + environment + submission posture + known institute targets) locks down the funding strategy before any search runs. Runs a 5-face...

Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.

Model agent mental states using BDI (Beliefs, Desires, Intentions) ontology patterns, enabling cognitive reasoning, explainability, and semantic interoperability in multi-agent systems.

Audit Android component configurations and Intent handling to prevent Intent Redirection and unauthorized access.

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

当需要进入高度专注、高效且愉悦的心流状态以完成创造性或学习性任务时

Systematically collects, categorizes, and distributes indicators of compromise (IOCs) during and after security incidents to enable detection, blocking, and threat intelligence sharing.

Route a task to the most fitting skill or agent. Parses user intent, checks installed-skill inventory, and picks the best match (single skill or chain).

Find adjacent vendors and subs (not top market primes) who fill a capability gap against a displacement target using USASpending flows and SAM entity signals. Use when user defines a teaming gap and wants vault-ready partner shortlist with citations.

Hunt for registry-based persistence mechanisms including Run keys, Winlogon modifications, IFEO injection, and COM hijacking in Windows environments.

基于 anchor 论文、topic 关键词或当前 wiki 状态，产出一份排好序的候选论文 shortlist，供用户或上游 skill 决定是否进一步 `/ingest`。当用户问 "接下来该读什么"、"找和这篇相似的论文"、"推荐相关工作"、"这个方向周围有什么" 时触发；`/ingest --discover` 也会内部调用本 skill。本身不 ingest，只提出候选。

Patent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search / freedom-to-operate / competitive landscape / acquisition diligence / litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.